Maximizing Operator Impact: Leveraging Machine Learning to Improve Trending Analysis for the Magnetospheric Multiscale (MMS) Mission
Explore the source record for details and available documents.
Shannon Bull↗
SEARCH · Engineering Papers
Results for “Operator learning”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Learning an Algebriac Multrigrid Interpolation Operator Using a Modified GraphNet Architecture
This work, building on previous efforts, develops a suite of new graph neural network machine learning architectures that generate data-driven prolongators for use in Algebraic Multigrid (AMG). Algebraic Multigrid is a powerful and common technique for solving large, sparse linear systems. Its effectiveness is problem dependent and heavily depends on the choice of the prolongation operator, which interpolates the coarse mesh results onto a finer mesh. Previous work has used recent developments in graph neural networks to learn a prolongation operator from a given coefficient matrix. In this paper, we expand on previous work by exploring architectural enhancements of graph neural networks. A new method for generating a training set is developed which more closely aligns to the test set. Asymptotic error reduction factors are compared on a test suite of 3-dimensional Poisson problems with varying degrees of element stretching. Results show modest improvements in asymptotic error factor over both commonly chosen baselines and learning methods from previous work.
97 MATHEMATICS AND COMPUTING↗
An Assessment of the Usability of Machine Learning Based Tools for the Security Operations Center
Gartner, a large research and advisory company, anticipates that by 2024 80% of security operation centers (SOCs) will use machine learning (ML) based solutions to enhance their operations. 1 1 https://www.ciodive.com/news/how-data-science-tools-can-lighten-the-load-for-cybersecurity-teams/572209/ In light of such widespread adoption, it is vital for the research community to identify and address usability concerns. This work presents the results of the first in situ usability assessment of ML-based tools. With the support of the US Navy, we leveraged the national cyber range-a large, air-gapped cyber testbed equipped with state-of-the-art network and user emulation capabilities-to study six US Naval SOC analysts' usage of two tools. Our analysis identified several serious usability issues, including multiple violations of established usability heuristics for user interface design. We also discovered that analysts lacked a clear mental model of how these tools generate scores, resulting in mistrust a and/or misuse of the tools themselves. Surprisingly, we found no correlation between analysts' level of education or years of experience and their performance with either tool, suggesting that other factors such as prior background knowledge or personality play a significant role in ML-based tool usage. Our findings demonstrate that ML-based security tool vendors must put a renewed focus on working with analysts, both experienced and inexperienced, to ensure that their systems are usable and useful in real-world security operations settings.
Oesch, T↗
Active Learning with Rationales for Identifying Operationally Significant Anomalies in Aviation
A major focus of the commercial aviation community is discovery of unknown safety events in flight operations data. Data-driven unsupervised anomaly detection methods are better at capturing unknown safety events compared to rule-based methods which only look for known violations. However, not all statistical anomalies that are discovered by these unsupervised anomaly detection methods are operationally significant (e.g., represent a safety concern). Subject Matter Experts (SMEs) have to spend significant time reviewing these statistical anomalies individually to identify a few operationally significant ones. In this paper we propose an active learning algorithm that incorporates SME feedback in the form of rationales to build a classifier that can distinguish between uninteresting and operationally significant anomalies. Experimental evaluation on real aviation data shows that our approach improves detection of operationally significant events by as much as 75% compared to the state-of-the-art. The learnt classifier also generalizes well to additional validation data sets.
anomaly detection↗
Digital Learning Network Education Events of NASA's Extreme Environments Mission Operations
NASA's Digital Learning Network (DLN) reaches out to thousands of students each year through video conferencing and web casting. The DLN has created a series of live education videoconferences connecting NASA s Extreme Environment Missions Operations (NEEMO) team to students across the United States. The programs are also extended to students around the world live web casting. The primary focus of the events is the vision for space exploration. During the programs, NEEMO Crewmembers including NASA astronauts, engineers and scientists inform and inspire students about the importance of exploration and share the impact of the project as it correlates with plans to return to the moon and explore the planet Mars. These events highlight interactivity. Students talk live with the aquanauts in Aquarius, the National Oceanic and Atmospheric Administration s underwater laboratory. With this program, NASA continues the Agency s tradition of investing in the nation's education programs. It is directly tied to the Agency's major education goal of attracting and retaining students in science, technology, and engineering disciplines. Before connecting with the aquanauts, the students conduct experiments of their own designed to coincide with mission objectives. This paper describes the events that took place in September 2006.
Paul, Heather↗
Collaborating Fuzzy Reinforcement Learning Agents
Earlier, we introduced GARIC-Q, a new method for doing incremental Dynamic Programming using a society of intelligent agents which are controlled at the top level by Fuzzy Relearning and at the local level, each agent learns and operates based on ANTARCTIC, a technique for fuzzy reinforcement learning. In this paper, we show that it is possible for these agents to compete in order to affect the selected control policy but at the same time, they can collaborate while investigating the state space. In this model, the evaluator or the critic learns by observing all the agents behaviors but the control policy changes only based on the behavior of the winning agent also known as the super agent.
Berenji, Hamid R.↗
Synthetic Biologic Membrane
The International Space Station (ISS) is a test bed for the technologies that will be used to travel to Mars and beyond. The lessons learned from operating the ISS provide valuable direction to future research and technology development programs. One of the most critical and complicated subsystems on ISS is the life support system. The life support system keeps the crew alive by recycling both air and water. The ISS water recycling system has been operating since 2009 and one of the main lessons learned is that reliability is a key technology performance metric. In the long run reliability is a key cost driver and is a critical factor in insuring crew safety. For long duration missions such as the exploration of Mars, where resupply of spare parts from Earth is difficult if not impossible, reliability is even more important. This presentation will cover research into improving the reliability of ISS systems. It will discuss research into the development of a biomimetic membrane materials that provides self-regeneration capabilities for water recycling systems. It will also cover research into past failures of the ISS water recycling system caused by astronaut bone loss and the build-up of trace contaminates in the cabin.
Biology↗
Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations
As part of the Research Institute for Computing and Information Systems (RICIS) activity, the reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Max satellite simulation. This activity is carried out in the software technology laboratory utilizing the Orbital Operations Simulator (OOS). This interim report provides the status of the project and outlines the future plans.
Jani, Yashvant↗
Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study
Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a complete theoretical framework for understanding these scaling laws remains underdeveloped. In this paper, we explore the neural scaling laws for deep operator networks, which involve learning mappings between function spaces, with a focus on the Chen and Chen style architecture. These approaches, which include the popular Deep Operator Network (DeepONet), approximate the output functions using a linear combination of learnable basis functions and coefficients that depend on the input functions. We establish a theoretical framework to quantify the neural scaling laws by analyzing its approximation and generalization errors. We articulate the relationship between the approximation and generalization errors of deep operator networks and key factors such as network model size and training data size. Moreover, we address cases where input functions exhibit low-dimensional structures, allowing us to derive tighter error bounds. These results also hold for deep ReLU networks and other similar structures. Our results offer a partial explanation of the neural scaling laws in operator learning and provide a theoretical foundation for their applications.
97 MATHEMATICS AND COMPUTING↗
Lessons Learned from the Stardust Sample Return Mission
These are science and mission design and operations lessons learned from the Stardust Mission, which returned grains from comet Wild-2 and fresh interstellar dust to Earth in 2006 [1]. Science Lessons: Major discoveries of the Stardust Wild-2 samples include the presence of numerous chondrules and CAI in a comet, which requires a much more dynamic early solar system than many had envisaged, and verified predictions made by models requiring outward flow of early solar system solids before the early nebular gas had dissipated [1-3]. No evidence has been found for the presence of live Al-26 in the comet, suggesting late accretion [4]. Carbonates and unusual sulfides were found which potentially require activity of liquid water within the comet, but to only a minor degree at best [5-6]. The presence of abundant thermally-metamorphosed silicates in Wild-2 appears to require assembly from an earlier generation of bodies [7]. The abundance of presolar grains in the Wild-2 samples appears to be below what has been found in most chondritic IDPs and primitive chondrites [1]. The bulk mineralogy of Wild-2 grains does not match the mineralogy from any single other known astromaterial [7], and is also strikingly unlike that inferred from Spitzer Telescope spectra of Comet Temple 1 dust [8]. Amino acids and other fragile organics have been detected among the Wild-2 samples [9], which highlights the critical importance of further developing techniques for organic analysis in small samples, and cleaning outbound spacecraft.
Zolensky, M. E.↗
Micrometer: Micromechanics transformer for predicting full field mechanical responses of heterogeneous materials
Predicting mechanical responses of heterogeneous materials across scales remains a significant challenge. Traditional computational methods often struggle with complex and multiscale nature of these materials, limiting their effectiveness in real-world applications. Here, in this paper, we introduce Micrometer, a vision transformer based deep learning model designed to predict full field mechanical responses of heterogeneous materials, bridging the gap between computer vision and solid mechanics problems. We show that Micrometer, trained on a large-scale high-resolution dataset of 2D fiber-reinforced composites, can achieve state-of-the-art performance in predicting microscale strain fields across a wide range of material properties and loading conditions. Our model demonstrates accuracy and computational efficiency in applications such as computational homogenization and multiscale modeling, reducing computational time by up to two orders of magnitude compared to conventional numerical solvers while maintaining less than 1 % errors in predicting macroscale stress fields. Furthermore, we showcase Micrometer’s adaptability through transfer learning experiments on new materials with limited data, highlighting its potential to tackle diverse scenarios in computational solid mechanics. These results represent a significant step towards AI-driven innovation in materials science, addressing the limitations of traditional numerical methods and paving the way for more efficient simulations of heterogeneous materials across various industrial applications.
Composite materials↗
Operational Evolution of FTS3: A DevOps Driven Approach to Elastic Operations
The File Transfer Service (FTS3) is a distributed data movement service developed at CERN and widely used to transfer data across the Worldwide LHC Computing Grid (WLCG). At Fermilab, FTS3 supports data transfers for multiple experiments, including Intensity Frontier experiments such as DUNE, enabling reliable data movement between WebDAV endpoints in Europe and the Americas. At CHEP 2021, we reported on the initial containerized deployment of FTS3 on OKD, the community Kubernetes distribution of Red Hat OpenShift. In this work, we present the subsequent evolution of this deployment, focusing on new operational capabilities introduced to improve scalability, robustness, and long-term maintainability. We describe the adoption of more secure and reproducible container build workflows, the integration of DevOps-driven operational practices, and enhancements in monitoring and automation. A key new result is the introduction of horizontal scaling and elastic resource management, allowing FTS3 components to dynamically adapt to workload variations while maintaining service reliability. We also discuss improvements in fault tolerance and operational procedures derived from production experience. Finally, we summarize lessons learned from operating FTS3 as a Kubernetes-native service and outline how these developments have improved the resilience and efficiency of data movement operations at Fermilab.
Munoz Flores, Victor Leopoldo [Fermilab]↗
Real Time Data System (RTDS)
Lessons learned from operational real time expert systems are examined. The basic system architecture is discussed. An expert system is any software that performs tasks to a standard that would normally require a human expert. An expert system implies knowledge contained in data rather than code. And an expert system implies the use of heuristics as well as algorithms. The 15 top lessons learned by the operation of a real time data system are presented.
Muratore, John F.↗
Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians
In this paper we propose a new Koopman operator approach for nonlinear model decomposition using Koopman gramians. We introduce Koopman operators and discuss the notion of a input-Koopman operator. We show how input-Koopman operators can be used to cast a nonlinear system into the classical state-space form, as well as conditions under which input and state observable functions are well separated. We extend an existing method of dynamic mode decomposition for learning Koopman operators from data known as deep dynamic mode decomposition, for systems with control or disturbances. We illustrate the accuracy of the method on learning an input-state separable Koopman operator for an example system, even when the underlying system exhibits mixed state-input terms. Finally, we introduce a nonlinear decomposition algorithm, based on Koopman gramians, that maximizes internal subsystem observability and disturbance rejection from unwanted noise in other subsystems. To relieve the NP-hardness of the decomposition problem, we derive a relaxation based on Koopman gramians and multi-way partitioning. We illustrate our algorithm on a swing dynamics model for a IEEE 39 bus and discuss our findings.
Learning, Control, Distributed Control, koopman op↗
ACTS Ka-Band Earth Stations: Technology, Performance, and Lessons Learned
The Advanced Communications Technology Satellite (ACTS) Project invested heavily in prototype Ka-band satellite ground terminals to conduct an experiments program with the ACTS satellite. The ACTS experiment's program proposed to validate Ka-band satellite and ground station technology. demonstrate future telecommunication services. demonstrate commercial viability and market acceptability of these new services, evaluate system networking and processing technology, and characterize Ka-band propagation effects, including development of techniques to mitigate signal fading. This paper will present a summary of the fixed ground terminals developed by the NASA Glenn Research Center and its industry partners, emphasizing the technology and performance of the terminals (Part 1) and the lessons learned throughout their six year operation including the inclined orbit phase of operations (Full Report). An overview of the Ka-band technology and components developed for the ACTS ground stations is presented. Next. the performance of the ground station technology and its evolution during the ACTS campaign are discussed to illustrate the technical tradeoffs made during the program and highlight technical advances by industry to support the ACTS experiments program and terminal operations. Finally. lessons learned during development and operation of the user terminals are discussed for consideration of commercial adoption into future Ka-band systems. The fixed ground stations used for experiments by government, academic, and commercial entities used reflector based offset-fed antenna systems ranging in size from 0.35m to 3.4m antenna diameter. Gateway earth stations included two systems, referred to as the NASA Ground Station (NGS) and the Link Evaluation Terminal (LET). The NGS provides tracking, telemetry, and control (TT&C) and Time Division Multiple Access (TDMA) network control functions. The LET supports technology verification and high data rate experiments. The ground stations successfully demonstrated many services and applications at Ka-band in three different modes of operation: circuit switched TDMA using the satellite on-board processor, satellite switched SS-TDMA applications using the on-board Microwave Switch Matrix (MSM), and conventional transponder (bent-pipe) operation. Data rates ranged from 4.8 kbps up to 622 Mbps. Experiments included: 1) low rate (4.8- 1 00's kbps) remote data acquisition and control using small earth stations, 2) moderate rate (1-45 Mbps) experiments included full duplex voice and video conferencing and both full duplex and asymmetric data rate protocol and network evaluation using mid-size ground stations, and 3) link characterization experiments and high data rate (155-622 Mbps) terrestrial and satellite interoperability application experiments conducted by a consortium of experimenters using the large transportable ground stations.
Reinhart, Richard C.↗
Lessons Learned in the First Year Operating Software Defined Radios in Space
Operating three unique software defined radios (SDRs) in a space environment aboard the Space Communications and Navigation (SCaN) Testbed for over one year has provided an opportunity to gather knowledge useful for future missions considering using software defined radios. This paper provides recommendations for the development and use of SDRs, and it considers the details of each SDRs approach to software upgrades and operation. After one year, the SCaN Testbed SDRs have operated for over 1000 hours. During this time, the waveforms launched with the SDR were tested on-orbit to assure that they operated in space at the same performance level as on the ground prior to launch to obtain an initial on-orbit performance baseline. A new waveform for each SDR has been developed, implemented, uploaded to the flight system, and tested in the flight environment. Recommendations for SDR-based missions have been gathered from early development through operations. These recommendations will aid future missions to reduce the cost, schedule, and risk of operating SDRs in a space environment. This paper considers the lessons learned as they apply to SDR pre-launch checkout, purchasing space-rated hardware, flexibility in command and telemetry methods, on-orbit diagnostics, use of engineering models to aid future development, and third-party software. Each SDR implements the SCaN Testbed flight computer command and telemetry interface uniquely, allowing comparisons to be drawn. The paper discusses the lessons learned from these three unique implementations, with suggestions on the preferred approach. Also, results are presented showing that it is important to have full system performance knowledge prior to launch to establish better performance baselines in space, requiring additional test applications to be developed pre-launch. Finally, the paper presents the issues encountered with the operation and implementation of new waveforms on each SDR and proposes recommendations to avoid these issues.
radio equipment↗
Lessons Learned in the First Year Operating Software Defined Radios in Space
Operating three unique software defined radios (SDRs) in a space environment aboard the Space Communications and Navigation (SCaN) Testbed for over one year has provided an opportunity to gather knowledge useful for future missions considering using software defined radios. This paper provides recommendations for the development and use of SDRs, and it considers the details of each SDR's approach to software upgrades and operation. After one year, the SCaN Testbed SDRs have operated for over 1000 hours. During this time, the waveforms launched with the SDR were tested on-orbit to assure that they operated in space at the same performance level as on the ground prior to launch to obtain an initial on-orbit performance baseline. A new waveform for each SDR has been developed, implemented, uploaded to the flight system, and tested in the flight environment. Recommendations for SDR-based missions have been gathered from early development through operations. These recommendations will aid future missions to reduce the cost, schedule, and risk of operating SDRs in a space environment. This paper considers the lessons learned as they apply to SDR pre-launch checkout, purchasing space-rated hardware, flexibility in command and telemetry methods, on-orbit diagnostics, use of engineering models to aid future development, and third-party software. Each SDR implements the SCaN Testbed flight computer command and telemetry interface uniquely, allowing comparisons to be drawn. The paper discusses the lessons learned from these three unique implementations, with suggestions on the preferred approach. Also, results are presented showing that it is important to have full system performance knowledge prior to launch to establish better performance baselines in space, requiring additional test applications to be developed pre-launch. Finally, the paper presents the issues encountered with the operation and implementation of new waveforms on each SDR and proposes recommendations to avoid these issues.
space communication↗
Toward fully automated UED operation using two-stage machine learning model
To demonstrate the feasibility of automating UED operation and diagnosing the machine performance in real time, a two-stage machine learning (ML) model based on self-consistent start-to-end simulations has been implemented. This model will not only provide the machine parameters with adequate precision, toward the full automation of the UED instrument, but also make real-time electron beam information available as single-shot nondestructive diagnostics. Furthermore, based on a deep understanding of the root connection between the electron beam properties and the features of Bragg-diffraction patterns, we have applied the hidden symmetry as model constraints, successfully improving the accuracy of energy spread prediction by a factor of five and making the beam divergence prediction two times faster. The capability enabled by the global optimization via ML provides us with better opportunities for discoveries using near-parallel, bright, and ultrafast electron beams for single-shot imaging. It also enables directly visualizing the dynamics of defects and nanostructured materials, which is impossible using present electron-beam technologies.
36 MATERIALS SCIENCE↗